Elastic Inference PNG and SVG Icon
Amazon Elastic Inference allows you to attach low-cost GPU-powered inference acceleration to Amazon EC2 and SageMaker instances.
Last Modified: August 29, 2025
16px
32px
48px
64px
Details
Key Features
- Attach GPU-powered inference acceleration to EC2 and SageMaker.
- Reduces ML inference costs by scaling GPU capacity as needed.
- Supports TensorFlow, Apache MXNet, and PyTorch.
- Pay only for the acceleration hours used.
Common Use Cases
- Reducing inference costs by attaching partial GPUs
- Accelerating deep learning model predictions
- Optimizing real-time AI workloads
Explore More Icons
MariaDB Instance
MariaDB Instance in Amazon RDS allows you to run managed MariaDB databases with automated backups, patching, and scaling.
Classic Load Balancer
Classic Load Balancer is the legacy Elastic Load Balancing option for distributing incoming traffic across EC2 instances.
Data Firehose
Amazon Kinesis Data Firehose is a fully managed service for delivering real-time streaming data to destinations like Amazon S3, Redshift, and OpenSearch.
Data Exchange
AWS Data Exchange is a service that makes it easy to find, subscribe to, and use third-party data in the cloud securely and efficiently.
Elemental MediaPackage
AWS Elemental MediaPackage prepares and protects video for delivery over the internet to connected devices.
SQS Queue
Amazon SQS Queue is a scalable message queuing service that enables decoupling and communication between microservices, distributed systems, and serverless applications.
Clean Rooms
AWS Clean Rooms is a privacy-enhancing collaboration service that enables multiple parties to analyze their collective data without sharing raw data.
Panorama
AWS Panorama is a machine learning appliance and SDK that enables you to run computer vision models on on-premises cameras and video streams.
Lex
Amazon Lex is a service for building conversational interfaces using voice and text, powered by the same deep learning technology as Alexa.
HTTP Notification
AWS HTTP Notification typically refers to using Amazon SNS or EventBridge to send notifications via HTTP endpoints in real-time.
Direct Connect
AWS Direct Connect provides a dedicated network connection from your premises to AWS, offering consistent, low-latency performance.
Location Service
Amazon Location Service helps developers add location-based features such as maps, tracking, and geofencing to applications without compromising data security.
Elemental MediaLive
AWS Elemental MediaLive is a broadcast-grade live video processing service that lets you create live outputs for streaming and broadcasting.
VPC Lattice
Amazon VPC Lattice helps you securely connect, monitor, and manage service-to-service communication in a consistent way.
Elemental Conductor
AWS Elemental Conductor is software for managing multiple AWS Elemental Live encoders from a central interface.
CloudShell
AWS CloudShell is a browser-based shell that provides command-line access to AWS services and tools directly from the AWS Management Console.
Hosted Zone
A Hosted Zone in Amazon Route 53 is a container for records that define how traffic is routed for a domain and its subdomains.
Elemental Live
AWS Elemental Live is a real-time video and audio encoding solution that compresses live video for broadcast and streaming delivery.
Neuron
AWS Neuron is a software development kit (SDK) that enables running high-performance ML models on AWS Inferentia-based instances.
Managed Service for Prometheus
Amazon Managed Service for Prometheus is a fully managed, scalable, and secure monitoring service for container metrics using Prometheus.
Lightsail
Amazon Lightsail is an easy-to-use cloud platform that provides virtual servers, storage, and networking for simpler workloads and small businesses.
Elastic Fabric Adapter
Elastic Fabric Adapter (EFA) is a network interface for EC2 instances that enables low-latency, high-throughput communication for HPC and ML workloads.
Thinkbox Krakatoa
Thinkbox Krakatoa is a volumetric particle rendering and manipulation software used in high-end VFX and simulation rendering.
Notebook
Amazon SageMaker Notebook is a fully managed Jupyter notebook environment for developing, training, and deploying machine learning models.